Over time, many individuals have been exposed to chemical substances with potentially harmful effects on the human body, making drug toxicity a critical factor in drug development process. High toxicity remains a primary cause of drug failure during clinical trials. Therefore, toxicity testing has become a main focus in the medical field to prevent further exposure to hazardous chemicals. The study focuses on predicting the toxicity of androgen receptor ligand-binding domain (AR-LBD) compounds by implementing Long Short-Term Memory (LSTM) model optimized by Simulated Annealing (SA). The methodology includes several steps, such as dataset preparation from the Tox21 Data Challenge, model training using the SA-optimized LSTM, performance evaluation against traditional toxicity prediction methods, and validation through testing datasets. The proposed model demonstrated impressive results, achieving an F1-score of 0.7105 and an accuracy 0.9782 outperforming traditional prediction models and the baseline without SA